Forecasting new development of tumor areas using spatial and temporal distribution profiles of hemoglobin saturation in a mouse model

Miguel R. Ossandon; Dhananjay S. Phatak; Brian S. Sorg; Konstantinos Kalpakis

doi:10.1117/1.JMI.1.1.014503

20 June 2014 Forecasting new development of tumor areas using spatial and temporal distribution profiles of hemoglobin saturation in a mouse model

Miguel R. Ossandon, Dhananjay S. Phatak, Brian S. Sorg, Konstantinos Kalpakis

Author Affiliations +

Journal of Medical Imaging, Vol. 1, Issue 1, 014503 (June 2014). https://doi.org/10.1117/1.JMI.1.1.014503

Abstract

Features of the tumor microenvironment (TME), such as hemoglobin saturation (HbSat), can provide valuable information on early development and progression of tumors. HbSat correlates with high metabolism and precedes the formation of angiogenic tumors; therefore, changes in HbSat profile can be used as a biomarker for early cancer detection. In this project, we develop a methodology to evaluate HbSat for forecasting early tumor development in a mouse model. We built a delta (δ ) cumulative feature that includes spatial and temporal distribution of HbSat for classifying tumor/normal areas. Using a two-class (normal and tumor) logistic regression, the δ feature successfully forecasts tumor areas in two window chamber mice (AUC=0.90 and 0.85). To assess the performance of the logistic regression-based classifier utilizing the δ feature of each region, we conduct a 10-fold cross-validation analysis (AUC of the ROC=0.87 ). These results show that the TME features based on HbSat can be used to evaluate tumor progression and forecast new occurrences of tumor areas.

Citation Download Citation

Miguel R. Ossandon, Dhananjay S. Phatak, Brian S. Sorg, and Konstantinos Kalpakis "Forecasting new development of tumor areas using spatial and temporal distribution profiles of hemoglobin saturation in a mouse model," Journal of Medical Imaging 1(1), 014503 (20 June 2014). https://doi.org/10.1117/1.JMI.1.1.014503

Published: 20 June 2014

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available